文章基本信息

标题：CLASSIFICATION OF IRIS IMAGE OF PATIENT CHRONIC RENAL FAILUR (CRF) USING WATERSHED ALGORITHM AND SUPPORT VECTOR MACHINE (SVM)
本地全文：下载
作者：ADHI. D. WIBAWA ; MAYA. A. R. SITORUS ; MAURIDHI. H. PURNOMO 等
期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2016
卷号：91
期号：2
出版社：Journal of Theoretical and Applied
摘要：Iridology is an alternative method in studying the condition of human internal organ through the image of iris. Iris chart has been introduced by scientists (Bernard Jensen) long time ago. In this paper we classified the iris image of patients CRF (Chronic Renal Failure) on stage 5 (End Stage of Renal Disease). Sixty one hemodialysis patients and 21 healthy volunteer with normal or nearest normal kidneys participated in this research. Iris image of CRF patients were taken using specific iris camera. Watershed transform technique was used to extract the features of iris image of hemodialysis patients. The ROI (region of interest) of iris image of renal organ is at 5.35-5.95 (2520 � 2680) for right eye and at 6.05-6.6 (2720 - 2880) for left eye assuming that the circle of iris is divided into 120 points (3600). The medical records of participants were used to validate the result of this study. The result showed that 87.5% of patients hemodialysis has shown broken tissue on their right iris and 89.3% has shown broken tissue on their left iris. In conclusion, the condition of renal organ of CRF patients mostly showed broken tissue in their iris image. SVM was used to recognize the iris image whether it contains broken tissue that showing kidney disease or not, and the accuracy showed that for learning and testing dataset, best mean of precission is 87.5% and best mean recall is 91.7% given by the percentage split 90 (where the data training was 90% and data testing was 10%).
关键词：Iridology; Iris Image Processing; Chronic Renal Failure; Watershed Algorithm; SVM